MODELING OF SPEECH SIGNALS USING AN OPTIMAL NEURAL-NETWORK STRUCTURE-BASED ON THE PMDL PRINCIPLE

Citation
Xm. Gao et al., MODELING OF SPEECH SIGNALS USING AN OPTIMAL NEURAL-NETWORK STRUCTURE-BASED ON THE PMDL PRINCIPLE, IEEE transactions on speech and audio processing, 6(2), 1998, pp. 177-180
Citations number
10
Categorie Soggetti
Engineering, Eletrical & Electronic",Acoustics
ISSN journal
10636676
Volume
6
Issue
2
Year of publication
1998
Pages
177 - 180
Database
ISI
SICI code
1063-6676(1998)6:2<177:MOSSUA>2.0.ZU;2-E
Abstract
Although neural networks have already found many successful applicatio ns in speech signal processing, it is difficult to compare their perfo rmance with that of the traditional methods objectively, In this corre spondence, we address this problem by using the predictive minimum des cription length (PMDL) principle to select the optimal network size in modeling speech signals.